Inferring Facility Planograms

1. A method comprising: causing each of multiple cameras within a facility to generate image data of a respective area of the facility, the multiple cameras including a first camera having a field-of-view (FOV) of a first area of the facility, the first area including a first inventory location and a second inventory location; storing, in one or more datastores, first planogram data indicating that a first item identifier of a first item is associated with the first inventory location; receiving, after storing the first planogram data, first data indicating that a first user has acquired an item from the first inventory location; storing a first association between the first user and the first item identifier; acquiring first image data generated by the first camera; analyzing, using one or more computer-vision algorithms, the first image data to identify a first portion of the first image data corresponding to the first inventory location and a second portion of the first image data corresponding to the second inventory location; analyzing, using the one or more computer-vision algorithms, the first image data to determine that the first portion of the first image data represents a second item; storing, in the one or more datastores, second planogram data indicating that a second item identifier of the second item is associated with the first inventory location; receiving, after storing the second planogram data, second data indicating that a second user has acquired an item from the first inventory location; and storing a second association between the second user and the second item identifier.

2. The method as recited in claim 1, further comprising: receiving, after storing the first planogram data and prior to storing the second planogram data, an indication that an item has been placed at the inventory location; and wherein the analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data comprises analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data at least partly in response to the receiving of the indication that the item has been placed at the inventory location.

3. The method as recited in claim 1, further comprising: detecting, based at least in part on sensor data generated by one or more sensors in the facility, a planogram change; and wherein the analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data comprises analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data at least partly in response to the detecting of the planogram change.

4. The method as recited in claim 1, further comprising: receiving, after storing the first planogram data and prior to storing the second planogram data, data indicating the second item identifier or another item identifier associated with the second item has been received from a mobile device of an associate of the facility; and wherein the analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data comprises analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data at least partly in response to the receiving of the data indicating the second item identifier or the another item identifier associated with the second item has been received from the mobile device of the associate of the facility.

5. The method as recited in claim 1, further comprising sending sensor data generated by one or more sensors in the facility to one or more mobile devices in the facility.

6. The method as recited in claim 1, wherein the analyzing, using the one or more computer-vision algorithms, the first image data to determine that the first portion of the first image data represents the second item comprises generating first feature data based at least in part on the second item and comparing the first feature data to respective feature data associated with one or more other items.

7. The method as recited in claim 1, further comprising: storing first timestamp data indicating a first time range associated with the first planogram data; and storing second timestamp data indicating a second time range associated with the second planogram data.

8. A system comprising: one or more processors; one or more datastores; and one or more computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform acts comprising: causing each of multiple cameras within a facility to generate image data of a respective portion of the facility; storing, in the one or more datastores, first planogram data indicating that a first item causing each of multiple cameras within a facility to generate image data of a respective area of the facility, the multiple cameras including a first camera having a field-of-view (FOV) of a first area of the facility, the first area including a first inventory location and a second inventory location; storing, in one or more datastores, first planogram data indicating that a first item identifier of a first item is associated with the first inventory location; receiving, after storing the first planogram data, first data indicating that a first user has acquired an item from the first inventory location; storing a first association between the first user and the first item identifier; acquiring first image data generated by the first camera; analyzing, using one or more computer-vision algorithms, the first image data to identify a first portion of the first image data corresponding to the first inventory location and a second portion of the first image data corresponding to the second inventory location; analyzing, using the one or more computer-vision algorithms, the first image data to determine that the first portion of the first image data represents a second item; storing, in the one or more datastores, second planogram data indicating that a second item identifier of the second item is associated with the first inventory location; receiving, after storing the second planogram data, second data indicating that a second user has acquired an item from the first inventory location; and storing a second association between the second user and the second item identifier.

9. The system as recited in claim 8, the acts further comprising: receiving, after storing the first planogram data and prior to storing the second planogram data, an indication that an item has been placed at the inventory location; and wherein the analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data comprises analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data at least partly in response to the receiving of the indication that the item has been placed at the inventory location.

10. The system as recited in claim 8, the acts further comprising: detecting, based at least in part on sensor data generated by one or more sensors in the facility, a planogram change; and wherein the analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data comprises analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data at least partly in response to the detecting of the planogram change.

11. The system as recited in claim 8, the acts further comprising: receiving, after storing the first planogram data and prior to storing the second planogram data, data indicating the second item identifier or another item identifier associated with the second item has been received from a mobile device of an associate of the facility; and wherein the analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data comprises analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data at least partly in response to the receiving of the data indicating the second item identifier or the another item identifier associated with the second item has been received from the mobile device of the associate of the facility.

12. The system as recited in claim 8, the acts further comprising sending sensor data generated by one or more sensors in the facility to one or more mobile devices in the facility.

13. The system as recited in claim 8, wherein the analyzing, using the one or more computer-vision algorithms, the first image data to determine that the first portion of the first image data represents the second item comprises generating first feature data based at least in part on the second item and comparing the first feature data to respective feature data associated with one or more other items.

14. The system as recited in claim 8, the acts further comprising: storing first timestamp data indicating a first time range associated with the first planogram data; and storing second timestamp data indicating a second time range associated with the second planogram data.

15. One or more non-transitory computer-readable media storing computer-executable instructions that, when executed, cause one or more processors to perform acts comprising: causing each of multiple cameras within a facility to generate image data of a respective portion of the facility; storing, in one or more datastores, first planogram data indicating that a first item causing each of multiple cameras within a facility to generate image data of a respective area of the facility, the multiple cameras including a first camera having a field-of-view (FOV) of a first area of the facility, the first area including a first inventory location and a second inventory location; storing, in one or more datastores, first planogram data indicating that a first item identifier of a first item is associated with the first inventory location; receiving, after storing the first planogram data, first data indicating that a first user has acquired an item from the first inventory location; storing a first association between the first user and the first item identifier; acquiring first image data generated by the first camera; analyzing, using one or more computer-vision algorithms, the first image data to identify a first portion of the first image data corresponding to the first inventory location and a second portion of the first image data corresponding to the second inventory location; analyzing, using the one or more computer-vision algorithms, the first image data to determine that the first portion of the first image data represents a second item; storing, in the one or more datastores, second planogram data indicating that a second item identifier of the second item is associated with the first inventory location; receiving, after storing the second planogram data, second data indicating that a second user has acquired an item from the first inventory location; and storing a second association between the second user and the second item identifier.

16. The one or more non-transitory computer-readable media as recited in claim 15, the acts further comprising: receiving, after storing the first planogram data and prior to storing the second planogram data, an indication that an item has been placed at the inventory location; and wherein the analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data comprises analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data at least partly in response to the receiving of the indication that the item has been placed at the inventory location.

17. The one or more non-transitory computer-readable media as recited in claim 15, the acts further comprising: detecting, based at least in part on sensor data generated by one or more sensors in the facility, a planogram change; and wherein the analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data comprises analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data at least partly in response to the detecting of the planogram change.

18. The one or more non-transitory computer-readable media as recited in claim 15, the acts further comprising: receiving, after storing the first planogram data and prior to storing the second planogram data, data indicating the second item identifier or another item identifier associated with the second item has been received from a mobile device of an associate of the facility; and wherein the analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data comprises analyzing the first image data to identify the first portion of the first image data and the second portion of the first image data at least partly in response to the receiving of the data indicating the second item identifier or the another item identifier associated with the second item has been received from the mobile device of the associate of the facility.

19. The one or more non-transitory computer-readable media as recited in claim 15, the acts further comprising sending sensor data generated by one or more sensors in the facility to one or more mobile devices in the facility.

20. The one or more non-transitory computer-readable media as recited in claim 15, the acts further comprising: storing first timestamp data indicating a first time range associated with the first planogram data; and storing second timestamp data indicating a second time range associated with the second planogram data.